⚠ Switch to EXCALIDRAW VIEW in the MORE OPTIONS menu of this document. ⚠ You can decompress Drawing data with the command palette: ‘Decompress current Excalidraw file’. For more info check in plugin settings under ‘Saving’

Excalidraw Data

Text Elements

%%

Drawing

{
  "type": "excalidraw",
  "version": 2,
  "source": "https://github.com/zsviczian/obsidian-excalidraw-plugin",
  "elements": [
    {
      "id": "title-main", "type": "text", "x": 80, "y": 18, "width": 840, "height": 35,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5001, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "ControlAudio:渐进扩散建模 — 三阶段训练 + 渐进引导采样", "fontSize": 24, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "ControlAudio:渐进扩散建模 — 三阶段训练 + 渐进引导采样", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "data-title", "type": "text", "x": 40, "y": 70, "width": 280, "height": 22,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5101, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "📦 数据构建(标注 + 模拟)", "fontSize": 16, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "middle", "containerId": null,
      "originalText": "📦 数据构建(标注 + 模拟)", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "data-annotate-box", "type": "rectangle", "x": 40, "y": 100, "width": 200, "height": 100,
      "angle": 0, "strokeColor": "#a5d8ff", "backgroundColor": "#a5d8ff", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 5201, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "data-annotate-text", "type": "text", "x": 50, "y": 108, "width": 180, "height": 84,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5202, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "标注管线\nAudioSet-SL → 双分离\n→ Gemini 2.5 Pro 转录\n152k 高质量事件", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "标注管线\nAudioSet-SL → 双分离\n→ Gemini 2.5 Pro 转录\n152k 高质量事件", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "data-sim-box", "type": "rectangle", "x": 280, "y": 100, "width": 200, "height": 100,
      "angle": 0, "strokeColor": "#a5d8ff", "backgroundColor": "#b2f2bb", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 5301, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "data-sim-text", "type": "text", "x": 290, "y": 108, "width": 180, "height": 84,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5302, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "模拟管线\nLibriTTS-R 语音\n+ WavCaps/VGG 背景\n171k 复杂场景 (SNR 2-10dB)", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "模拟管线\nLibriTTS-R 语音\n+ WavCaps/VGG 背景\n171k 复杂场景 (SNR 2-10dB)", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "data-prompt-box", "type": "rectangle", "x": 520, "y": 100, "width": 240, "height": 100,
      "angle": 0, "strokeColor": "#d0bfff", "backgroundColor": "#d0bfff", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 5401, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "data-prompt-text", "type": "text", "x": 530, "y": 108, "width": 220, "height": 84,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5402, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "统一语义建模\n单一 Flan-T5 编码 text\n+ timing + phoneme\n@{} 结构化提示 + 音素 token", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "统一语义建模\n单一 Flan-T5 编码 text\n+ timing + phoneme\n@{} 结构化提示 + 音素 token", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "train-title", "type": "text", "x": 40, "y": 220, "width": 280, "height": 22,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5501, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "🔄 渐进模型训练(三阶段)", "fontSize": 16, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "middle", "containerId": null,
      "originalText": "🔄 渐进模型训练(三阶段)", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "stage1-box", "type": "rectangle", "x": 40, "y": 252, "width": 230, "height": 110,
      "angle": 0, "strokeColor": "#a5d8ff", "backgroundColor": "#a5d8ff", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 5601, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "stage1-text", "type": "text", "x": 50, "y": 260, "width": 210, "height": 70,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5602, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "Stage 1: TTA 预训练\n条件: text only\n大规模文本-音频对\n1M steps · DiT 骨干\n建立通用 TTA 能力", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "Stage 1: TTA 预训练\n条件: text only\n大规模文本-音频对\n1M steps · DiT 骨干\n建立通用 TTA 能力", "autoResize": true, "lineHeight": 1.25
    },
    {
      "id": "stage1-label", "type": "text", "x": 60, "y": 240, "width": 60, "height": 18,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "#a5d8ff", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5603, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "🔥 冻结", "fontSize": 11, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "🔥 冻结", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "arrow1", "type": "arrow", "x": 270, "y": 307, "width": 40, "height": 0,
      "angle": 0, "strokeColor": "#ffd8a8", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 3, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5701, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "points": [[0, 0], [40, 0]]
    },
 
    {
      "id": "stage2-box", "type": "rectangle", "x": 310, "y": 252, "width": 230, "height": 110,
      "angle": 0, "strokeColor": "#ffd8a8", "backgroundColor": "#ffd8a8", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 5801, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "stage2-text", "type": "text", "x": 320, "y": 260, "width": 210, "height": 70,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5802, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "Stage 2: 时间控制微调\n条件: text + timing\n条件随机切换防遗忘\n0.5M steps\n精确时间窗口控制", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "Stage 2: 时间控制微调\n条件: text + timing\n条件随机切换防遗忘\n0.5M steps\n精确时间窗口控制", "autoResize": true, "lineHeight": 1.25
    },
    {
      "id": "stage2-label", "type": "text", "x": 330, "y": 240, "width": 60, "height": 18,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "#ffd8a8", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5803, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "🔥 冻结", "fontSize": 11, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "🔥 冻结", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "arrow2", "type": "arrow", "x": 540, "y": 307, "width": 40, "height": 0,
      "angle": 0, "strokeColor": "#ffd8a8", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 3, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 5901, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "points": [[0, 0], [40, 0]]
    },
 
    {
      "id": "stage3-box", "type": "rectangle", "x": 580, "y": 252, "width": 230, "height": 110,
      "angle": 0, "strokeColor": "#b2f2bb", "backgroundColor": "#b2f2bb", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 6001, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "stage3-text", "type": "text", "x": 590, "y": 260, "width": 210, "height": 70,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6002, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "Stage 3: 联合训练\n条件: text + timing + phoneme\n解冻 Flan-T5 联合优化\n0.5M steps · 三条件随机切换", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "Stage 3: 联合训练\n条件: text + timing + phoneme\n解冻 Flan-T5 联合优化\n0.5M steps · 三条件随机切换", "autoResize": true, "lineHeight": 1.25
    },
    {
      "id": "stage3-label", "type": "text", "x": 600, "y": 240, "width": 60, "height": 18,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "#b2f2bb", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6003, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "🔓 解冻", "fontSize": 11, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "🔓 解冻", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "infer-title", "type": "text", "x": 40, "y": 385, "width": 280, "height": 22,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6101, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "🎯 渐进引导采样(推理)", "fontSize": 16, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "middle", "containerId": null,
      "originalText": "🎯 渐进引导采样(推理)", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "infer-noise", "type": "ellipse", "x": 60, "y": 430, "width": 60, "height": 40,
      "angle": 0, "strokeColor": "#a5d8ff", "backgroundColor": "#e0e0e0", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6201, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "infer-noise-text", "type": "text", "x": 65, "y": 440, "width": 50, "height": 20,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6202, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "z_T ~ N", "fontSize": 11, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "z_T ~ N", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "infer-arrow1", "type": "arrow", "x": 120, "y": 450, "width": 80, "height": 0,
      "angle": 0, "strokeColor": "#ffd8a8", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6301, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "points": [[0, 0], [80, 0]]
    },
 
    {
      "id": "phase1-box", "type": "rectangle", "x": 200, "y": 420, "width": 260, "height": 60,
      "angle": 0, "strokeColor": "#ffd8a8", "backgroundColor": "#ffd8a8", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 6401, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "phase1-text", "type": "text", "x": 210, "y": 425, "width": 240, "height": 50,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6402, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "Phase 1: 时序结构建立\nt ∈ [1.0, 88]\n条件: text + timing (无音素)\nw_low = 3", "fontSize": 12, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "Phase 1: 时序结构建立\nt ∈ [1.0, 88]\n条件: text + timing (无音素)\nw_low = 3", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "infer-arrow2", "type": "arrow", "x": 460, "y": 450, "width": 80, "height": 0,
      "angle": 0, "strokeColor": "#b2f2bb", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6501, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "points": [[0, 0], [80, 0]]
    },
 
    {
      "id": "phase2-box", "type": "rectangle", "x": 540, "y": 420, "width": 270, "height": 60,
      "angle": 0, "strokeColor": "#b2f2bb", "backgroundColor": "#b2f2bb", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 6601, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "phase2-text", "type": "text", "x": 550, "y": 425, "width": 250, "height": 50,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6602, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "Phase 2: 语音内容渲染\nt ∈ (88, 0]\n条件: text + timing + phoneme\nw_high = 9", "fontSize": 12, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "Phase 2: 语音内容渲染\nt ∈ (88, 0]\n条件: text + timing + phoneme\nw_high = 9", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "infer-arrow3", "type": "arrow", "x": 810, "y": 450, "width": 60, "height": 0,
      "angle": 0, "strokeColor": "#b2f2bb", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6701, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "points": [[0, 0], [60, 0]]
    },
 
    {
      "id": "infer-output", "type": "ellipse", "x": 870, "y": 430, "width": 60, "height": 40,
      "angle": 0, "strokeColor": "#b2f2bb", "backgroundColor": "#b2f2bb", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6801, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "infer-output-text", "type": "text", "x": 875, "y": 440, "width": 50, "height": 20,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6802, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "z_0 → x", "fontSize": 11, "fontFamily": 5,
      "textAlign": "center", "verticalAlign": "middle", "containerId": null,
      "originalText": "z_0 → x", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "results-title", "type": "text", "x": 40, "y": 510, "width": 350, "height": 22,
      "angle": 0, "strokeColor": "#1e40af", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 6901, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "📊 核心结果(ACL 2026 Main)", "fontSize": 16, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "middle", "containerId": null,
      "originalText": "📊 核心结果(ACL 2026 Main)", "autoResize": true, "lineHeight": 1.25
    },
 
    {
      "id": "results-box", "type": "rectangle", "x": 40, "y": 540, "width": 800, "height": 70,
      "angle": 0, "strokeColor": "#d0bfff", "backgroundColor": "#f0e6ff", "fillStyle": "solid",
      "strokeWidth": 2, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": {"type": 3}, "seed": 7001, "version": 1, "isDeleted": false, "boundElements": [],
      "updated": 1, "link": null, "locked": false
    },
    {
      "id": "results-text", "type": "text", "x": 55, "y": 548, "width": 770, "height": 54,
      "angle": 0, "strokeColor": "#1e3a5f", "backgroundColor": "transparent", "fillStyle": "solid",
      "strokeWidth": 1, "strokeStyle": "solid", "roughness": 0, "opacity": 100, "groupIds": [],
      "roundness": null, "seed": 7002, "version": 1, "isDeleted": false, "boundElements": null,
      "updated": 1, "link": null, "locked": false,
      "text": "AudioCondition: Eb 55.58 (SOTA) / At 79.52 (SOTA) | AC-Filtered: WER 6.84 (SOTA) | AudioCaps: FAD 1.56 (持平 Stable Audio)\n10 类事件 8 类最优 · Speech 类 Eb 39→64 · 可控性不牺牲基础 TTA 质量", "fontSize": 13, "fontFamily": 5,
      "textAlign": "left", "verticalAlign": "top", "containerId": null,
      "originalText": "AudioCondition: Eb 55.58 (SOTA) / At 79.52 (SOTA) | AC-Filtered: WER 6.84 (SOTA) | AudioCaps: FAD 1.56 (持平 Stable Audio)\n10 类事件 8 类最优 · Speech 类 Eb 39→64 · 可控性不牺牲基础 TTA 质量", "autoResize": true, "lineHeight": 1.25
    }
  ],
  "appState": {
    "gridSize": 20,
    "gridStep": 5,
    "gridModeEnabled": false,
    "viewBackgroundColor": "#ffffff"
  },
  "files": {}
}